Large language models (LLMs) are increasingly being used for the task of automated code translation, which has important real-world applications. However, most existing approaches use only the source code of a program as an input to an LLM, and do not consider the different kinds of specifications that can be extracted from a program. In this paper, we propose SpecTra, a multi-stage approach that uses a novel self-consistency filter to first generate high-quality invariants, test cases, and natural language descriptions from a given program, and then uses these along with the source code to improve the quality of LLM-generated translations. We evaluate SpecTra on two code translation tasks - C to Rust, and C to Go - and show that it can enhance the performance of four popular LLMs on these tasks by up to 10 percentage points and a relative improvement of up to 23%. Our research suggests that generating high-quality specifications could be a promising and efficient way to improve the performance of LLMs for code translation.
翻译:暂无翻译